Exploratory Data Analysis On Electric Vehicle¶

What is Exploratory Data Analysis?¶

  • Exploratory Data Analysis (EDA) is the process of analyzing a dataset in order to understand its main characteristics, patterns and identify anomalies. EDA is often the first step in the data analysis process.

  • It involves using different graphs and plots to help visualise the data and also uses statistical methods to draw inferences from the data.

  • The goal of EDA is not to arrive at a certain right answer or to confirm a pre-defined hypothesis. It is an exploratory process to draw inferences and get ideas on how the data can be further utilised to predict certain outcomes/develop ML models

  • An electric vehicle (EV) is a vehicle that uses one or more electric motors for propulsion. It can be powered by a collector system, with electricity from extravehicular sources, or it can be powered autonomously by a battery (sometimes charged by solar panels, or by converting fuel to electricity using fuel cells or a generator).

  • EVs include, but are not limited to, road and rail vehicles, surface and underwater vessels, electric aircraft , and electric spacecraft.

  • For road vehicles, together with other emerging automotive technologies such as autonomous driving, connected vehicles, and shared mobility, EVs form a future mobility vision called Connected, Autonomous, Shared, and Electric (CASE) Mobility.
  • EVs first came into existence in the late 19th century, when electricity was among the preferred methods for motor vehicle propulsion, providing a level of comfort and ease of operation that could not be achieved by the gasoline cars of the time.

  • Internal combustion engines were the dominant propulsion method for cars and trucks for about 100 years, but electric power remained commonplace in other vehicle types, such as trains and smaller vehicles of all types.

  • Data set link : https://drive.google.com/file/d/1P742LU5OTXbfFG2F6drbABk1O8UGf4Cd/view?usp=sharing ## About Dataset This dataset shows the Battery Electric Vehicles (BEVs) and Plug-in Hybrid Electric Vehicles (PHEVs) that are currently registered through the Washington State Department of Licensing (DOL).

1.A Battery Electric Vehicle (BEV) is an all-electric vehicle using one or more batteries to store the electrical energy that powers the motor and is charged by plugging the vehicle into an electric power source.

2 Alternative Fuel Vehicle (CAFV) Eligibility is based on the fuel requirement and electric-only range requirement as outlined in RCW 82.08.809 and RCW 82.12.809 to be eligible for Alternative Fuel Vehicles retail sales and Washington State use tax exemptions.

3.Monthly count of vehicles for a county may change from this report and prior reports. Processes were implemented to more accurately assign county at the time of registration.

4.Electric Range is no longer maintained for Battery Electric Vehicles (BEV) because new BEVs have an electric range of 30 miles or more. Zero (0) will be entered where the electric range has not been researched.

5.Field 'Electric Utility' was added starting with the publication in March 2022.

6.Field '2020 Census Tract' was added starting with the publication in June 2022.

In [ ]:

Importing Required Libraries¶

In [59]:
import pandas as pd
import numpy as np
import plotly.express as px
import warnings
warnings.filterwarnings("ignore")
import matplotlib.pyplot as plt

df=pd.read_csv(r"C:\Users\Irfan\Downloads\dataset.csv")

df
Out[59]:
VIN (1-10) County City State Postal Code Model Year Make Model Electric Vehicle Type Clean Alternative Fuel Vehicle (CAFV) Eligibility Electric Range Base MSRP Legislative District DOL Vehicle ID Vehicle Location Electric Utility 2020 Census Tract
0 JTMEB3FV6N Monroe Key West FL 33040 2022 TOYOTA RAV4 PRIME Plug-in Hybrid Electric Vehicle (PHEV) Clean Alternative Fuel Vehicle Eligible 42 0 NaN 198968248 POINT (-81.80023 24.5545) NaN 12087972100
1 1G1RD6E45D Clark Laughlin NV 89029 2013 CHEVROLET VOLT Plug-in Hybrid Electric Vehicle (PHEV) Clean Alternative Fuel Vehicle Eligible 38 0 NaN 5204412 POINT (-114.57245 35.16815) NaN 32003005702
2 JN1AZ0CP8B Yakima Yakima WA 98901 2011 NISSAN LEAF Battery Electric Vehicle (BEV) Clean Alternative Fuel Vehicle Eligible 73 0 15.0 218972519 POINT (-120.50721 46.60448) PACIFICORP 53077001602
3 1G1FW6S08H Skagit Concrete WA 98237 2017 CHEVROLET BOLT EV Battery Electric Vehicle (BEV) Clean Alternative Fuel Vehicle Eligible 238 0 39.0 186750406 POINT (-121.7515 48.53892) PUGET SOUND ENERGY INC 53057951101
4 3FA6P0SU1K Snohomish Everett WA 98201 2019 FORD FUSION Plug-in Hybrid Electric Vehicle (PHEV) Not eligible due to low battery range 26 0 38.0 2006714 POINT (-122.20596 47.97659) PUGET SOUND ENERGY INC 53061041500
... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ...
112629 7SAYGDEF2N King Duvall WA 98019 2022 TESLA MODEL Y Battery Electric Vehicle (BEV) Eligibility unknown as battery range has not b... 0 0 45.0 217955265 POINT (-121.98609 47.74068) PUGET SOUND ENERGY INC||CITY OF TACOMA - (WA) 53033032401
112630 1N4BZ1CP7K San Juan Friday Harbor WA 98250 2019 NISSAN LEAF Battery Electric Vehicle (BEV) Clean Alternative Fuel Vehicle Eligible 150 0 40.0 103663227 POINT (-123.01648 48.53448) BONNEVILLE POWER ADMINISTRATION||ORCAS POWER &... 53055960301
112631 1FMCU0KZ4N King Vashon WA 98070 2022 FORD ESCAPE Plug-in Hybrid Electric Vehicle (PHEV) Clean Alternative Fuel Vehicle Eligible 38 0 34.0 193878387 POINT (-122.4573 47.44929) PUGET SOUND ENERGY INC||CITY OF TACOMA - (WA) 53033027702
112632 KNDCD3LD4J King Covington WA 98042 2018 KIA NIRO Plug-in Hybrid Electric Vehicle (PHEV) Not eligible due to low battery range 26 0 47.0 125039043 POINT (-122.09124 47.33778) PUGET SOUND ENERGY INC||CITY OF TACOMA - (WA) 53033032007
112633 YV4BR0CL8N King Covington WA 98042 2022 VOLVO XC90 Plug-in Hybrid Electric Vehicle (PHEV) Not eligible due to low battery range 18 0 47.0 194673692 POINT (-122.09124 47.33778) PUGET SOUND ENERGY INC||CITY OF TACOMA - (WA) 53033032005

112634 rows × 17 columns

In [2]:
df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 112634 entries, 0 to 112633
Data columns (total 17 columns):
 #   Column                                             Non-Null Count   Dtype  
---  ------                                             --------------   -----  
 0   VIN (1-10)                                         112634 non-null  object 
 1   County                                             112634 non-null  object 
 2   City                                               112634 non-null  object 
 3   State                                              112634 non-null  object 
 4   Postal Code                                        112634 non-null  int64  
 5   Model Year                                         112634 non-null  int64  
 6   Make                                               112634 non-null  object 
 7   Model                                              112614 non-null  object 
 8   Electric Vehicle Type                              112634 non-null  object 
 9   Clean Alternative Fuel Vehicle (CAFV) Eligibility  112634 non-null  object 
 10  Electric Range                                     112634 non-null  int64  
 11  Base MSRP                                          112634 non-null  int64  
 12  Legislative District                               112348 non-null  float64
 13  DOL Vehicle ID                                     112634 non-null  int64  
 14  Vehicle Location                                   112610 non-null  object 
 15  Electric Utility                                   112191 non-null  object 
 16  2020 Census Tract                                  112634 non-null  int64  
dtypes: float64(1), int64(6), object(10)
memory usage: 14.6+ MB
In [3]:
df.duplicated().sum()
Out[3]:
0
In [4]:
print(len(df.columns))
df.columns

17
Out[4]:
Index(['VIN (1-10)', 'County', 'City', 'State', 'Postal Code', 'Model Year',
       'Make', 'Model', 'Electric Vehicle Type',
       'Clean Alternative Fuel Vehicle (CAFV) Eligibility', 'Electric Range',
       'Base MSRP', 'Legislative District', 'DOL Vehicle ID',
       'Vehicle Location', 'Electric Utility', '2020 Census Tract'],
      dtype='object')
In [5]:
df.head()
Out[5]:
VIN (1-10) County City State Postal Code Model Year Make Model Electric Vehicle Type Clean Alternative Fuel Vehicle (CAFV) Eligibility Electric Range Base MSRP Legislative District DOL Vehicle ID Vehicle Location Electric Utility 2020 Census Tract
0 JTMEB3FV6N Monroe Key West FL 33040 2022 TOYOTA RAV4 PRIME Plug-in Hybrid Electric Vehicle (PHEV) Clean Alternative Fuel Vehicle Eligible 42 0 NaN 198968248 POINT (-81.80023 24.5545) NaN 12087972100
1 1G1RD6E45D Clark Laughlin NV 89029 2013 CHEVROLET VOLT Plug-in Hybrid Electric Vehicle (PHEV) Clean Alternative Fuel Vehicle Eligible 38 0 NaN 5204412 POINT (-114.57245 35.16815) NaN 32003005702
2 JN1AZ0CP8B Yakima Yakima WA 98901 2011 NISSAN LEAF Battery Electric Vehicle (BEV) Clean Alternative Fuel Vehicle Eligible 73 0 15.0 218972519 POINT (-120.50721 46.60448) PACIFICORP 53077001602
3 1G1FW6S08H Skagit Concrete WA 98237 2017 CHEVROLET BOLT EV Battery Electric Vehicle (BEV) Clean Alternative Fuel Vehicle Eligible 238 0 39.0 186750406 POINT (-121.7515 48.53892) PUGET SOUND ENERGY INC 53057951101
4 3FA6P0SU1K Snohomish Everett WA 98201 2019 FORD FUSION Plug-in Hybrid Electric Vehicle (PHEV) Not eligible due to low battery range 26 0 38.0 2006714 POINT (-122.20596 47.97659) PUGET SOUND ENERGY INC 53061041500
In [6]:
df.shape
Out[6]:
(112634, 17)

unique values¶

In [7]:
cols = df.columns
def Unique_Values():
    for i in np.arange(0,len(cols)):
        print('{} column have {} number of unique values  out of {}'.format( cols[i],df[cols[i]].nunique(), len(df)),end='\n\n')
Unique_Values()

VIN (1-10) column have 7548 number of unique values  out of 112634

County column have 165 number of unique values  out of 112634

City column have 629 number of unique values  out of 112634

State column have 45 number of unique values  out of 112634

Postal Code column have 773 number of unique values  out of 112634

Model Year column have 20 number of unique values  out of 112634

Make column have 34 number of unique values  out of 112634

Model column have 114 number of unique values  out of 112634

Electric Vehicle Type column have 2 number of unique values  out of 112634

Clean Alternative Fuel Vehicle (CAFV) Eligibility column have 3 number of unique values  out of 112634

Electric Range column have 101 number of unique values  out of 112634

Base MSRP column have 30 number of unique values  out of 112634

Legislative District column have 49 number of unique values  out of 112634

DOL Vehicle ID column have 112634 number of unique values  out of 112634

Vehicle Location column have 758 number of unique values  out of 112634

Electric Utility column have 73 number of unique values  out of 112634

2020 Census Tract column have 2026 number of unique values  out of 112634

Null values¶

In [8]:
cols = df.columns
def Null_Values():
    for i in np.arange(0,len(cols)):
        print('{} column have {} number of Null values  out of {}'.format( cols[i],df[cols[i]].isnull().sum(), len(df)),end='\n\n')
Null_Values()

VIN (1-10) column have 0 number of Null values  out of 112634

County column have 0 number of Null values  out of 112634

City column have 0 number of Null values  out of 112634

State column have 0 number of Null values  out of 112634

Postal Code column have 0 number of Null values  out of 112634

Model Year column have 0 number of Null values  out of 112634

Make column have 0 number of Null values  out of 112634

Model column have 20 number of Null values  out of 112634

Electric Vehicle Type column have 0 number of Null values  out of 112634

Clean Alternative Fuel Vehicle (CAFV) Eligibility column have 0 number of Null values  out of 112634

Electric Range column have 0 number of Null values  out of 112634

Base MSRP column have 0 number of Null values  out of 112634

Legislative District column have 286 number of Null values  out of 112634

DOL Vehicle ID column have 0 number of Null values  out of 112634

Vehicle Location column have 24 number of Null values  out of 112634

Electric Utility column have 443 number of Null values  out of 112634

2020 Census Tract column have 0 number of Null values  out of 112634
In [9]:
# to view the missing percentages
missing_percentges=df.isnull().sum()/len(df)
missing_percentges
Out[9]:
VIN (1-10)                                           0.000000
County                                               0.000000
City                                                 0.000000
State                                                0.000000
Postal Code                                          0.000000
Model Year                                           0.000000
Make                                                 0.000000
Model                                                0.000178
Electric Vehicle Type                                0.000000
Clean Alternative Fuel Vehicle (CAFV) Eligibility    0.000000
Electric Range                                       0.000000
Base MSRP                                            0.000000
Legislative District                                 0.002539
DOL Vehicle ID                                       0.000000
Vehicle Location                                     0.000213
Electric Utility                                     0.003933
2020 Census Tract                                    0.000000
dtype: float64

Handling The Missing Values¶

  • For handling the missing values we know the distributions of the variables by using statistics and vizualization techniques
  • To fill the null values
  • for numerical variables we use mean or median
  • Mean is impact with outliers if ouliers present in the data we use median.
  • if our data doesn't contain outliers then we use mean (to reduce the time complexity)
  • for categorical(object)we use mode

So in our data Model,Legislative District,Vehicle Location,Electric Utility columns having missing values.¶

  • numerical column - Legislative District
  • categorical columns -Model, Vehicle Location,Electric Utility
In [10]:
df.describe()
Out[10]:
Postal Code Model Year Electric Range Base MSRP Legislative District DOL Vehicle ID 2020 Census Tract
count 112634.000000 112634.000000 112634.000000 112634.000000 112348.000000 1.126340e+05 1.126340e+05
mean 98156.226850 2019.003365 87.812987 1793.439681 29.805604 1.994567e+08 5.296650e+10
std 2648.733064 2.892364 102.334216 10783.753486 14.700545 9.398427e+07 1.699104e+09
min 1730.000000 1997.000000 0.000000 0.000000 1.000000 4.777000e+03 1.101001e+09
25% 98052.000000 2017.000000 0.000000 0.000000 18.000000 1.484142e+08 5.303301e+10
50% 98119.000000 2020.000000 32.000000 0.000000 34.000000 1.923896e+08 5.303303e+10
75% 98370.000000 2022.000000 208.000000 0.000000 43.000000 2.191899e+08 5.305307e+10
max 99701.000000 2023.000000 337.000000 845000.000000 49.000000 4.792548e+08 5.603300e+10
In [11]:
#for numerical columns we have to check distributions for this we find outliers
px.box(df['Legislative District'],orientation='h')

To check the outliers by using IQR method(statistical_method)¶

In [12]:
q1=df['Legislative District'].quantile(0.25)

q3=df['Legislative District'].quantile(0.75)

iqr=q3-q1

lb=q1-1.5*iqr
ub=q1+1.5*iqr

df[(df['Legislative District']<=lb) | (df['Legislative District']>=ub)]
Out[12]:
VIN (1-10) County City State Postal Code Model Year Make Model Electric Vehicle Type Clean Alternative Fuel Vehicle (CAFV) Eligibility Electric Range Base MSRP Legislative District DOL Vehicle ID Vehicle Location Electric Utility 2020 Census Tract

Observation :¶

  • Here also we can observe that there are no ouliers in our data.`

Fillling null values with mean.¶

In [13]:
df['Legislative District']=df['Legislative District'].fillna(df['Legislative District'].mean())
In [14]:
(df[df['Model'].isnull()])
Out[14]:
VIN (1-10) County City State Postal Code Model Year Make Model Electric Vehicle Type Clean Alternative Fuel Vehicle (CAFV) Eligibility Electric Range Base MSRP Legislative District DOL Vehicle ID Vehicle Location Electric Utility 2020 Census Tract
13874 YV4ED3GM2P King Seattle WA 98115 2023 VOLVO NaN Battery Electric Vehicle (BEV) Eligibility unknown as battery range has not b... 0 0 46.0 221526476 POINT (-122.31765 47.70013) PUGET SOUND ENERGY INC||CITY OF TACOMA - (WA) 53033002200
30517 YV4ED3UL3P King Seattle WA 98115 2023 VOLVO NaN Battery Electric Vehicle (BEV) Eligibility unknown as battery range has not b... 0 0 43.0 223881556 POINT (-122.31765 47.70013) CITY OF SEATTLE - (WA)|CITY OF TACOMA - (WA) 53033003601
31936 YV4ED3GM4P Clallam Sequim WA 98382 2023 VOLVO NaN Battery Electric Vehicle (BEV) Eligibility unknown as battery range has not b... 0 0 24.0 219769000 POINT (-123.10367 48.07965) BONNEVILLE POWER ADMINISTRATION||PUD NO 1 OF C... 53009002301
37517 YV4ED3UW2P Snohomish Edmonds WA 98026 2023 VOLVO NaN Battery Electric Vehicle (BEV) Eligibility unknown as battery range has not b... 0 0 32.0 218357779 POINT (-122.31768 47.87166) PUGET SOUND ENERGY INC 53061050700
58071 YV4ED3UM4P King Renton WA 98058 2023 VOLVO NaN Battery Electric Vehicle (BEV) Eligibility unknown as battery range has not b... 0 0 11.0 224511766 POINT (-122.08747 47.4466) PUGET SOUND ENERGY INC||CITY OF TACOMA - (WA) 53033031911
61626 YV4ED3GM5P Pierce Tacoma WA 98465 2023 VOLVO NaN Battery Electric Vehicle (BEV) Eligibility unknown as battery range has not b... 0 0 28.0 224496702 POINT (-122.52886 47.24977) BONNEVILLE POWER ADMINISTRATION||CITY OF TACOM... 53053061001
63240 YV4ED3GMXP King Redmond WA 98052 2023 VOLVO NaN Battery Electric Vehicle (BEV) Eligibility unknown as battery range has not b... 0 0 48.0 221295224 POINT (-122.13158 47.67858) PUGET SOUND ENERGY INC||CITY OF TACOMA - (WA) 53033032324
63380 YV4ED3GM7P King Seattle WA 98122 2023 VOLVO NaN Battery Electric Vehicle (BEV) Eligibility unknown as battery range has not b... 0 0 37.0 224280472 POINT (-122.31009 47.60803) CITY OF SEATTLE - (WA)|CITY OF TACOMA - (WA) 53033007800
63462 YV4ED3UW4P King Newcastle WA 98059 2023 VOLVO NaN Battery Electric Vehicle (BEV) Eligibility unknown as battery range has not b... 0 0 41.0 218912410 POINT (-122.15771 47.50549) PUGET SOUND ENERGY INC||CITY OF TACOMA - (WA) 53033025005
78472 YV4ED3UM1P King Fall City WA 98024 2023 VOLVO NaN Battery Electric Vehicle (BEV) Eligibility unknown as battery range has not b... 0 0 5.0 224631494 POINT (-121.89086 47.56812) PUGET SOUND ENERGY INC||CITY OF TACOMA - (WA) 53033032221
81302 YV4ED3UM5P King Redmond WA 98052 2023 VOLVO NaN Battery Electric Vehicle (BEV) Eligibility unknown as battery range has not b... 0 0 48.0 220511791 POINT (-122.13158 47.67858) PUGET SOUND ENERGY INC||CITY OF TACOMA - (WA) 53033022902
84142 YV4ED3UM2P King North Bend WA 98045 2023 VOLVO NaN Battery Electric Vehicle (BEV) Eligibility unknown as battery range has not b... 0 0 5.0 223998148 POINT (-121.7831 47.49348) PUGET SOUND ENERGY INC||CITY OF TACOMA - (WA) 53033032704
86960 YV4ED3UM9P King Sammamish WA 98075 2023 VOLVO NaN Battery Electric Vehicle (BEV) Eligibility unknown as battery range has not b... 0 0 41.0 214714706 POINT (-122.03539 47.61344) PUGET SOUND ENERGY INC||CITY OF TACOMA - (WA) 53033032213
88687 YV4ED3GM5P King Maple Valley WA 98038 2023 VOLVO NaN Battery Electric Vehicle (BEV) Eligibility unknown as battery range has not b... 0 0 5.0 224709726 POINT (-122.04526 47.39394) PUGET SOUND ENERGY INC||CITY OF TACOMA - (WA) 53033031604
89882 YV4ED3UM5P King Bellevue WA 98006 2023 VOLVO NaN Battery Electric Vehicle (BEV) Eligibility unknown as battery range has not b... 0 0 41.0 214731254 POINT (-122.12096 47.55584) PUGET SOUND ENERGY INC||CITY OF TACOMA - (WA) 53033025007
93197 YV4ED3GM8P Snohomish Bothell WA 98021 2023 VOLVO NaN Battery Electric Vehicle (BEV) Eligibility unknown as battery range has not b... 0 0 1.0 220532063 POINT (-122.18384 47.8031) PUGET SOUND ENERGY INC 53061051926
103099 YV4ED3UW6P Pierce Milton WA 98354 2023 VOLVO NaN Battery Electric Vehicle (BEV) Eligibility unknown as battery range has not b... 0 0 30.0 213335454 POINT (-122.32172 47.24898) BONNEVILLE POWER ADMINISTRATION||CITY OF MILTO... 53053070703
103394 YV4ED3GM5P King Seattle WA 98133 2023 VOLVO NaN Battery Electric Vehicle (BEV) Eligibility unknown as battery range has not b... 0 0 46.0 220589967 POINT (-122.3503 47.71868) CITY OF SEATTLE - (WA)|CITY OF TACOMA - (WA) 53033000601
108116 YV4ED3GL1P King Seattle WA 98104 2023 VOLVO NaN Battery Electric Vehicle (BEV) Eligibility unknown as battery range has not b... 0 0 37.0 219268451 POINT (-122.32945 47.60357) CITY OF SEATTLE - (WA)|CITY OF TACOMA - (WA) 53033009300
112622 YV4ED3GM0P King Covington WA 98042 2023 VOLVO NaN Battery Electric Vehicle (BEV) Eligibility unknown as battery range has not b... 0 0 47.0 224307996 POINT (-122.09124 47.33778) PUGET SOUND ENERGY INC||CITY OF TACOMA - (WA) 53033031709
In [15]:
crosstab=pd.crosstab(df['Make'],df['Model'])
crosstab
Out[15]:
Model 330E 500 530E 740E 745E 745LE 918 A3 A7 A8 E ... TRANSIT CONNECT ELECTRIC TUCSON V60 VOLT WRANGLER X3 X5 XC40 XC60 XC90
Make
AUDI 0 0 0 0 0 0 0 575 11 3 ... 0 0 0 0 0 0 0 0 0 0
AZURE DYNAMICS 0 0 0 0 0 0 0 0 0 0 ... 7 0 0 0 0 0 0 0 0 0
BENTLEY 0 0 0 0 0 0 0 0 0 0 ... 0 0 0 0 0 0 0 0 0 0
BMW 303 0 323 30 7 2 0 0 0 0 ... 0 0 0 0 0 292 1407 0 0 0
CADILLAC 0 0 0 0 0 0 0 0 0 0 ... 0 0 0 0 0 0 0 0 0 0
CHEVROLET 0 0 0 0 0 0 0 0 0 0 ... 0 0 0 4896 0 0 0 0 0 0
CHRYSLER 0 0 0 0 0 0 0 0 0 0 ... 0 0 0 0 0 0 0 0 0 0
FIAT 0 822 0 0 0 0 0 0 0 0 ... 0 0 0 0 0 0 0 0 0 0
FISKER 0 0 0 0 0 0 0 0 0 0 ... 0 0 0 0 0 0 0 0 0 0
FORD 0 0 0 0 0 0 0 0 0 0 ... 0 0 0 0 0 0 0 0 0 0
GENESIS 0 0 0 0 0 0 0 0 0 0 ... 0 0 0 0 0 0 0 0 0 0
HONDA 0 0 0 0 0 0 0 0 0 0 ... 0 0 0 0 0 0 0 0 0 0
HYUNDAI 0 0 0 0 0 0 0 0 0 0 ... 0 38 0 0 0 0 0 0 0 0
JAGUAR 0 0 0 0 0 0 0 0 0 0 ... 0 0 0 0 0 0 0 0 0 0
JEEP 0 0 0 0 0 0 0 0 0 0 ... 0 0 0 0 1104 0 0 0 0 0
KIA 0 0 0 0 0 0 0 0 0 0 ... 0 0 0 0 0 0 0 0 0 0
LAND ROVER 0 0 0 0 0 0 0 0 0 0 ... 0 0 0 0 0 0 0 0 0 0
LEXUS 0 0 0 0 0 0 0 0 0 0 ... 0 0 0 0 0 0 0 0 0 0
LINCOLN 0 0 0 0 0 0 0 0 0 0 ... 0 0 0 0 0 0 0 0 0 0
LUCID MOTORS 0 0 0 0 0 0 0 0 0 0 ... 0 0 0 0 0 0 0 0 0 0
MERCEDES-BENZ 0 0 0 0 0 0 0 0 0 0 ... 0 0 0 0 0 0 0 0 0 0
MINI 0 0 0 0 0 0 0 0 0 0 ... 0 0 0 0 0 0 0 0 0 0
MITSUBISHI 0 0 0 0 0 0 0 0 0 0 ... 0 0 0 0 0 0 0 0 0 0
NISSAN 0 0 0 0 0 0 0 0 0 0 ... 0 0 0 0 0 0 0 0 0 0
POLESTAR 0 0 0 0 0 0 0 0 0 0 ... 0 0 0 0 0 0 0 0 0 0
PORSCHE 0 0 0 0 0 0 1 0 0 0 ... 0 0 0 0 0 0 0 0 0 0
RIVIAN 0 0 0 0 0 0 0 0 0 0 ... 0 0 0 0 0 0 0 0 0 0
SMART 0 0 0 0 0 0 0 0 0 0 ... 0 0 0 0 0 0 0 0 0 0
SUBARU 0 0 0 0 0 0 0 0 0 0 ... 0 0 0 0 0 0 0 0 0 0
TESLA 0 0 0 0 0 0 0 0 0 0 ... 0 0 0 0 0 0 0 0 0 0
TH!NK 0 0 0 0 0 0 0 0 0 0 ... 0 0 0 0 0 0 0 0 0 0
TOYOTA 0 0 0 0 0 0 0 0 0 0 ... 0 0 0 0 0 0 0 0 0 0
VOLKSWAGEN 0 0 0 0 0 0 0 0 0 0 ... 0 0 0 0 0 0 0 0 0 0
VOLVO 0 0 0 0 0 0 0 0 0 0 ... 0 0 12 0 0 0 0 495 702 820

34 rows × 114 columns

In [16]:
px.bar(crosstab,orientation='h',height=700)

In model we have missing values to fill these null values i choose condition based retrival¶

  • only one Volvo brand having the null values so from volvo we fingd mode of model that is "XC90" now we use these value for null values.
In [17]:
df['Model']=df['Model'].fillna("XC90")
In [18]:
df['Model'].isnull().sum()
Out[18]:
0
In [19]:
df[df['Vehicle Location'].isnull()]
Out[19]:
VIN (1-10) County City State Postal Code Model Year Make Model Electric Vehicle Type Clean Alternative Fuel Vehicle (CAFV) Eligibility Electric Range Base MSRP Legislative District DOL Vehicle ID Vehicle Location Electric Utility 2020 Census Tract
16 1N4AZ0CP4D Pierce Kapowsin WA 98344 2013 NISSAN LEAF Battery Electric Vehicle (BEV) Clean Alternative Fuel Vehicle Eligible 75 0 2.000000 237061968 NaN PUGET SOUND ENERGY INC||CITY OF TACOMA - (WA) 53053073119
9196 3FA6P0SU9E Hidalgo Mcallen TX 78501 2014 FORD FUSION Plug-in Hybrid Electric Vehicle (PHEV) Not eligible due to low battery range 19 0 29.805604 119899125 NaN NaN 48215020732
21728 5YJXCBE22G Allegheny Wexford PA 15090 2016 TESLA MODEL X Battery Electric Vehicle (BEV) Clean Alternative Fuel Vehicle Eligible 200 0 29.805604 177131685 NaN NaN 42003411002
26788 1N4BZ1CP7K Pierce Wilkeson WA 98396 2019 NISSAN LEAF Battery Electric Vehicle (BEV) Clean Alternative Fuel Vehicle Eligible 150 0 31.000000 476833899 NaN PUGET SOUND ENERGY INC||CITY OF TACOMA - (WA) 53053070206
29365 1G1FW6S08N Pacific Long Beach WA 98634 2022 CHEVROLET BOLT EV Battery Electric Vehicle (BEV) Eligibility unknown as battery range has not b... 0 0 19.000000 218102209 NaN BONNEVILLE POWER ADMINISTRATION||PUD NO 2 OF P... 53049950600
46475 5YJ3E1EA8J San Diego Oceanside CA 92051 2018 TESLA MODEL 3 Battery Electric Vehicle (BEV) Clean Alternative Fuel Vehicle Eligible 215 0 29.805604 153998050 NaN NaN 6073018509
61285 1FADP5CU5G Thurston Olympia WA 98507 2016 FORD C-MAX Plug-in Hybrid Electric Vehicle (PHEV) Not eligible due to low battery range 19 0 22.000000 339958097 NaN PUGET SOUND ENERGY INC 53067010100
64064 JN1AZ0CP6C King Seattle WA 98124 2012 NISSAN LEAF Battery Electric Vehicle (BEV) Clean Alternative Fuel Vehicle Eligible 73 0 11.000000 250994733 NaN CITY OF SEATTLE - (WA)|CITY OF TACOMA - (WA) 53033009300
66278 1C4JJXR67M Contra Costa Fpo CA 96349 2021 JEEP WRANGLER Plug-in Hybrid Electric Vehicle (PHEV) Not eligible due to low battery range 21 0 29.805604 187228030 NaN NaN 6013380001
67925 JN1AZ0CP6C King Seattle WA 98124 2012 NISSAN LEAF Battery Electric Vehicle (BEV) Clean Alternative Fuel Vehicle Eligible 73 0 11.000000 90772 NaN CITY OF SEATTLE - (WA)|CITY OF TACOMA - (WA) 53033009300
76199 KNDJX3AE8H Pacific Long Beach WA 98634 2017 KIA SOUL EV Battery Electric Vehicle (BEV) Clean Alternative Fuel Vehicle Eligible 93 32250 19.000000 106442773 NaN BONNEVILLE POWER ADMINISTRATION||PUD NO 2 OF P... 53049950501
76894 1G1RH6E48C Pierce Tacoma WA 98417 2012 CHEVROLET VOLT Plug-in Hybrid Electric Vehicle (PHEV) Clean Alternative Fuel Vehicle Eligible 35 0 27.000000 135454574 NaN BONNEVILLE POWER ADMINISTRATION||CITY OF TACOM... 53053060500
78460 1FADP5CU9D Kitsap Southworth WA 98386 2013 FORD C-MAX Plug-in Hybrid Electric Vehicle (PHEV) Not eligible due to low battery range 19 0 26.000000 213171388 NaN PUGET SOUND ENERGY INC 53035092704
82086 JTDKARFP7H Pierce Wilkeson WA 98396 2017 TOYOTA PRIUS PRIME Plug-in Hybrid Electric Vehicle (PHEV) Not eligible due to low battery range 25 0 31.000000 196771298 NaN PUGET SOUND ENERGY INC||CITY OF TACOMA - (WA) 53053070206
88188 JTDKN3DP5E Whatcom Bellingham WA 98227 2014 TOYOTA PRIUS PLUG-IN Plug-in Hybrid Electric Vehicle (PHEV) Not eligible due to low battery range 6 0 42.000000 136857493 NaN PUGET SOUND ENERGY INC||PUD NO 1 OF WHATCOM CO... 53073000600
96588 3FA6P0PU2D Pierce Wilkeson WA 98396 2013 FORD FUSION Plug-in Hybrid Electric Vehicle (PHEV) Not eligible due to low battery range 19 0 31.000000 226631765 NaN PUGET SOUND ENERGY INC||CITY OF TACOMA - (WA) 53053070206
98398 5YJXCBE2XG Thurston Lacey WA 98509 2016 TESLA MODEL X Battery Electric Vehicle (BEV) Clean Alternative Fuel Vehicle Eligible 200 0 22.000000 174187562 NaN PUGET SOUND ENERGY INC 53067011410
101160 JN1AZ0CP0B King Seattle WA 98124 2011 NISSAN LEAF Battery Electric Vehicle (BEV) Clean Alternative Fuel Vehicle Eligible 73 0 11.000000 165560762 NaN CITY OF SEATTLE - (WA)|CITY OF TACOMA - (WA) 53033009300
104056 5YJ3E1EC4L Rockingham Portsmouth NH 3804 2020 TESLA MODEL 3 Battery Electric Vehicle (BEV) Clean Alternative Fuel Vehicle Eligible 308 0 29.805604 8798226 NaN NaN 33015069200
105210 1FADP5CU9D Kitsap Southworth WA 98386 2013 FORD C-MAX Plug-in Hybrid Electric Vehicle (PHEV) Not eligible due to low battery range 19 0 26.000000 173023924 NaN PUGET SOUND ENERGY INC 53035092704
106748 JN1AZ0CP1B King Seattle WA 98124 2011 NISSAN LEAF Battery Electric Vehicle (BEV) Clean Alternative Fuel Vehicle Eligible 73 0 11.000000 101502166 NaN CITY OF SEATTLE - (WA)|CITY OF TACOMA - (WA) 53033009300
108694 KM8K23AG6M Pierce Tacoma WA 98401 2021 HYUNDAI KONA ELECTRIC Battery Electric Vehicle (BEV) Eligibility unknown as battery range has not b... 0 0 27.000000 157122437 NaN BONNEVILLE POWER ADMINISTRATION||CITY OF TACOM... 53053061601
110547 1G1RD6E41D Pierce Tacoma WA 98401 2013 CHEVROLET VOLT Plug-in Hybrid Electric Vehicle (PHEV) Clean Alternative Fuel Vehicle Eligible 38 0 27.000000 177221138 NaN BONNEVILLE POWER ADMINISTRATION||CITY OF TACOM... 53053061601
111234 3FMTK4SE6M Pierce Wilkeson WA 98396 2021 FORD MUSTANG MACH-E Battery Electric Vehicle (BEV) Eligibility unknown as battery range has not b... 0 0 31.000000 181410736 NaN PUGET SOUND ENERGY INC||CITY OF TACOMA - (WA) 53053070206
In [20]:
df['Electric Vehicle Type'].value_counts()
Out[20]:
Battery Electric Vehicle (BEV)            86044
Plug-in Hybrid Electric Vehicle (PHEV)    26590
Name: Electric Vehicle Type, dtype: int64
In [21]:
crosstab1=pd.crosstab(df['Vehicle Location'],df['Electric Vehicle Type'])
crosstab1['Battery Electric Vehicle (BEV)'].sort_values()
Out[21]:
Vehicle Location
POINT (7.86484 51.32975)          0
POINT (-118.01268 33.83899)       0
POINT (-121.92442 36.55443)       0
POINT (-117.97378 47.30036)       0
POINT (-117.90629 47.20139)       0
                               ... 
POINT (-122.21061 47.83448)    1538
POINT (-122.12096 47.55584)    1558
POINT (-122.1872 47.61001)     1718
POINT (-122.2066 47.67887)     1746
POINT (-122.13158 47.67858)    2485
Name: Battery Electric Vehicle (BEV), Length: 758, dtype: int64
In [22]:
crosstab1['Plug-in Hybrid Electric Vehicle (PHEV)'].sort_values()
Out[22]:
Vehicle Location
POINT (-102.69968 22.95716)      0
POINT (-76.8907 38.81605)        0
POINT (-118.50797 48.99237)      0
POINT (-118.59524 34.2271)       0
POINT (-76.73517 39.10852)       0
                              ... 
POINT (-122.521 47.62728)      331
POINT (-122.35436 47.67596)    354
POINT (-122.31765 47.70013)    407
POINT (-122.89166 47.03956)    413
POINT (-122.13158 47.67858)    431
Name: Plug-in Hybrid Electric Vehicle (PHEV), Length: 758, dtype: int64
In [23]:
px.box(crosstab1)
In [24]:
df['Vehicle Location']=df['Vehicle Location'].fillna(df['Vehicle Location'].mode()[0])
In [25]:
df['Electric Utility']=df['Electric Utility'].fillna(df['Electric Utility'].mode()[0])
In [26]:
df.isnull().sum()
Out[26]:
VIN (1-10)                                           0
County                                               0
City                                                 0
State                                                0
Postal Code                                          0
Model Year                                           0
Make                                                 0
Model                                                0
Electric Vehicle Type                                0
Clean Alternative Fuel Vehicle (CAFV) Eligibility    0
Electric Range                                       0
Base MSRP                                            0
Legislative District                                 0
DOL Vehicle ID                                       0
Vehicle Location                                     0
Electric Utility                                     0
2020 Census Tract                                    0
dtype: int64

outliers¶

In [27]:
df.columns
Out[27]:
Index(['VIN (1-10)', 'County', 'City', 'State', 'Postal Code', 'Model Year',
       'Make', 'Model', 'Electric Vehicle Type',
       'Clean Alternative Fuel Vehicle (CAFV) Eligibility', 'Electric Range',
       'Base MSRP', 'Legislative District', 'DOL Vehicle ID',
       'Vehicle Location', 'Electric Utility', '2020 Census Tract'],
      dtype='object')
In [28]:
num=df.select_dtypes(include='number')
In [29]:
num
Out[29]:
Postal Code Model Year Electric Range Base MSRP Legislative District DOL Vehicle ID 2020 Census Tract
0 33040 2022 42 0 29.805604 198968248 12087972100
1 89029 2013 38 0 29.805604 5204412 32003005702
2 98901 2011 73 0 15.000000 218972519 53077001602
3 98237 2017 238 0 39.000000 186750406 53057951101
4 98201 2019 26 0 38.000000 2006714 53061041500
... ... ... ... ... ... ... ...
112629 98019 2022 0 0 45.000000 217955265 53033032401
112630 98250 2019 150 0 40.000000 103663227 53055960301
112631 98070 2022 38 0 34.000000 193878387 53033027702
112632 98042 2018 26 0 47.000000 125039043 53033032007
112633 98042 2022 18 0 47.000000 194673692 53033032005

112634 rows × 7 columns

In [30]:
px.box(df['Base MSRP'])
In [31]:
q1=df['Base MSRP'].quantile(0.25)

q3=df['Base MSRP'].quantile(0.75)

iqr=q3-q1

lb=q1-1.5*iqr
ub=q1+1.5*iqr

df[(df['Base MSRP']>=lb) & (df['Base MSRP']>=200000)]
Out[31]:
VIN (1-10) County City State Postal Code Model Year Make Model Electric Vehicle Type Clean Alternative Fuel Vehicle (CAFV) Eligibility Electric Range Base MSRP Legislative District DOL Vehicle ID Vehicle Location Electric Utility 2020 Census Tract
62533 WP0CA2A13F King Hunts Point WA 98004 2015 PORSCHE 918 Plug-in Hybrid Electric Vehicle (PHEV) Not eligible due to low battery range 12 845000 48.0 100479039 POINT (-122.1872 47.61001) PUGET SOUND ENERGY INC||CITY OF TACOMA - (WA) 53033024100
In [32]:
df = df.drop(index=62533)
In [33]:
df.reset_index(drop='index',inplace=True)
In [34]:
df
Out[34]:
VIN (1-10) County City State Postal Code Model Year Make Model Electric Vehicle Type Clean Alternative Fuel Vehicle (CAFV) Eligibility Electric Range Base MSRP Legislative District DOL Vehicle ID Vehicle Location Electric Utility 2020 Census Tract
0 JTMEB3FV6N Monroe Key West FL 33040 2022 TOYOTA RAV4 PRIME Plug-in Hybrid Electric Vehicle (PHEV) Clean Alternative Fuel Vehicle Eligible 42 0 29.805604 198968248 POINT (-81.80023 24.5545) PUGET SOUND ENERGY INC||CITY OF TACOMA - (WA) 12087972100
1 1G1RD6E45D Clark Laughlin NV 89029 2013 CHEVROLET VOLT Plug-in Hybrid Electric Vehicle (PHEV) Clean Alternative Fuel Vehicle Eligible 38 0 29.805604 5204412 POINT (-114.57245 35.16815) PUGET SOUND ENERGY INC||CITY OF TACOMA - (WA) 32003005702
2 JN1AZ0CP8B Yakima Yakima WA 98901 2011 NISSAN LEAF Battery Electric Vehicle (BEV) Clean Alternative Fuel Vehicle Eligible 73 0 15.000000 218972519 POINT (-120.50721 46.60448) PACIFICORP 53077001602
3 1G1FW6S08H Skagit Concrete WA 98237 2017 CHEVROLET BOLT EV Battery Electric Vehicle (BEV) Clean Alternative Fuel Vehicle Eligible 238 0 39.000000 186750406 POINT (-121.7515 48.53892) PUGET SOUND ENERGY INC 53057951101
4 3FA6P0SU1K Snohomish Everett WA 98201 2019 FORD FUSION Plug-in Hybrid Electric Vehicle (PHEV) Not eligible due to low battery range 26 0 38.000000 2006714 POINT (-122.20596 47.97659) PUGET SOUND ENERGY INC 53061041500
... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ...
112628 7SAYGDEF2N King Duvall WA 98019 2022 TESLA MODEL Y Battery Electric Vehicle (BEV) Eligibility unknown as battery range has not b... 0 0 45.000000 217955265 POINT (-121.98609 47.74068) PUGET SOUND ENERGY INC||CITY OF TACOMA - (WA) 53033032401
112629 1N4BZ1CP7K San Juan Friday Harbor WA 98250 2019 NISSAN LEAF Battery Electric Vehicle (BEV) Clean Alternative Fuel Vehicle Eligible 150 0 40.000000 103663227 POINT (-123.01648 48.53448) BONNEVILLE POWER ADMINISTRATION||ORCAS POWER &... 53055960301
112630 1FMCU0KZ4N King Vashon WA 98070 2022 FORD ESCAPE Plug-in Hybrid Electric Vehicle (PHEV) Clean Alternative Fuel Vehicle Eligible 38 0 34.000000 193878387 POINT (-122.4573 47.44929) PUGET SOUND ENERGY INC||CITY OF TACOMA - (WA) 53033027702
112631 KNDCD3LD4J King Covington WA 98042 2018 KIA NIRO Plug-in Hybrid Electric Vehicle (PHEV) Not eligible due to low battery range 26 0 47.000000 125039043 POINT (-122.09124 47.33778) PUGET SOUND ENERGY INC||CITY OF TACOMA - (WA) 53033032007
112632 YV4BR0CL8N King Covington WA 98042 2022 VOLVO XC90 Plug-in Hybrid Electric Vehicle (PHEV) Not eligible due to low battery range 18 0 47.000000 194673692 POINT (-122.09124 47.33778) PUGET SOUND ENERGY INC||CITY OF TACOMA - (WA) 53033032005

112633 rows × 17 columns

In [35]:
px.box(df['Base MSRP'])

Task1 (Description) - Apply Exploratory Data Analysis(Univariate and Bivariate) using plotly.express library.¶

In [36]:
fig=px.histogram(df['Model Year'],orientation='v',text_auto=True)
fig.show()

Observation¶

  • Every year the frequency will be increased
In [37]:
cat=df.select_dtypes(exclude='number')
In [38]:
cat
Out[38]:
VIN (1-10) County City State Make Model Electric Vehicle Type Clean Alternative Fuel Vehicle (CAFV) Eligibility Vehicle Location Electric Utility
0 JTMEB3FV6N Monroe Key West FL TOYOTA RAV4 PRIME Plug-in Hybrid Electric Vehicle (PHEV) Clean Alternative Fuel Vehicle Eligible POINT (-81.80023 24.5545) PUGET SOUND ENERGY INC||CITY OF TACOMA - (WA)
1 1G1RD6E45D Clark Laughlin NV CHEVROLET VOLT Plug-in Hybrid Electric Vehicle (PHEV) Clean Alternative Fuel Vehicle Eligible POINT (-114.57245 35.16815) PUGET SOUND ENERGY INC||CITY OF TACOMA - (WA)
2 JN1AZ0CP8B Yakima Yakima WA NISSAN LEAF Battery Electric Vehicle (BEV) Clean Alternative Fuel Vehicle Eligible POINT (-120.50721 46.60448) PACIFICORP
3 1G1FW6S08H Skagit Concrete WA CHEVROLET BOLT EV Battery Electric Vehicle (BEV) Clean Alternative Fuel Vehicle Eligible POINT (-121.7515 48.53892) PUGET SOUND ENERGY INC
4 3FA6P0SU1K Snohomish Everett WA FORD FUSION Plug-in Hybrid Electric Vehicle (PHEV) Not eligible due to low battery range POINT (-122.20596 47.97659) PUGET SOUND ENERGY INC
... ... ... ... ... ... ... ... ... ... ...
112628 7SAYGDEF2N King Duvall WA TESLA MODEL Y Battery Electric Vehicle (BEV) Eligibility unknown as battery range has not b... POINT (-121.98609 47.74068) PUGET SOUND ENERGY INC||CITY OF TACOMA - (WA)
112629 1N4BZ1CP7K San Juan Friday Harbor WA NISSAN LEAF Battery Electric Vehicle (BEV) Clean Alternative Fuel Vehicle Eligible POINT (-123.01648 48.53448) BONNEVILLE POWER ADMINISTRATION||ORCAS POWER &...
112630 1FMCU0KZ4N King Vashon WA FORD ESCAPE Plug-in Hybrid Electric Vehicle (PHEV) Clean Alternative Fuel Vehicle Eligible POINT (-122.4573 47.44929) PUGET SOUND ENERGY INC||CITY OF TACOMA - (WA)
112631 KNDCD3LD4J King Covington WA KIA NIRO Plug-in Hybrid Electric Vehicle (PHEV) Not eligible due to low battery range POINT (-122.09124 47.33778) PUGET SOUND ENERGY INC||CITY OF TACOMA - (WA)
112632 YV4BR0CL8N King Covington WA VOLVO XC90 Plug-in Hybrid Electric Vehicle (PHEV) Not eligible due to low battery range POINT (-122.09124 47.33778) PUGET SOUND ENERGY INC||CITY OF TACOMA - (WA)

112633 rows × 10 columns

In [39]:
px.bar(df['County'][0:50],title='Top 50 countries')
In [40]:
px.bar(df['Make'][0:1000])

Observation:¶

  • TESLA having more intrested to manufacturing the electronic vehicle
In [41]:
px.bar(df['Electric Vehicle Type'][0:500])

Observation:¶

  • Most of the companies are using Battery ELectric Vehicles comparing witj plug-in-Hybrid electric vehicle

BI-VARIATE¶

In [42]:
px.scatter(x=df['Electric Range'],y=df['Base MSRP'],data_frame=df)
In [43]:
px.scatter(x=df['Model Year'],y=df['Electric Range'],data_frame=df)

Observation:¶

  • In the Model Year 2020 having the high electric range that is 337 compare to the other model years
In [44]:
px.box(x='Make',y='Electric Range',data_frame=df)

Observation¶

  • Tesla having the maximum electric range that is 337.
In [45]:
px.box(x=df['Make'],y=df['Base MSRP'],data_frame=df)
In [46]:
px.box(x=df['Make'],y=df['Model Year'],data_frame=df)

Observation:¶

  • KIA And Tesla most of average electrical vehicles released in 2021 model-year becuase the median is 2021
In [47]:
px.box(x=df['Electric Vehicle Type'],y=df['Electric Range'],data_frame=df)

Observation:¶

  • Battery Electric Vehicle have more electric range that is 337
In [48]:
cat
Out[48]:
VIN (1-10) County City State Make Model Electric Vehicle Type Clean Alternative Fuel Vehicle (CAFV) Eligibility Vehicle Location Electric Utility
0 JTMEB3FV6N Monroe Key West FL TOYOTA RAV4 PRIME Plug-in Hybrid Electric Vehicle (PHEV) Clean Alternative Fuel Vehicle Eligible POINT (-81.80023 24.5545) PUGET SOUND ENERGY INC||CITY OF TACOMA - (WA)
1 1G1RD6E45D Clark Laughlin NV CHEVROLET VOLT Plug-in Hybrid Electric Vehicle (PHEV) Clean Alternative Fuel Vehicle Eligible POINT (-114.57245 35.16815) PUGET SOUND ENERGY INC||CITY OF TACOMA - (WA)
2 JN1AZ0CP8B Yakima Yakima WA NISSAN LEAF Battery Electric Vehicle (BEV) Clean Alternative Fuel Vehicle Eligible POINT (-120.50721 46.60448) PACIFICORP
3 1G1FW6S08H Skagit Concrete WA CHEVROLET BOLT EV Battery Electric Vehicle (BEV) Clean Alternative Fuel Vehicle Eligible POINT (-121.7515 48.53892) PUGET SOUND ENERGY INC
4 3FA6P0SU1K Snohomish Everett WA FORD FUSION Plug-in Hybrid Electric Vehicle (PHEV) Not eligible due to low battery range POINT (-122.20596 47.97659) PUGET SOUND ENERGY INC
... ... ... ... ... ... ... ... ... ... ...
112628 7SAYGDEF2N King Duvall WA TESLA MODEL Y Battery Electric Vehicle (BEV) Eligibility unknown as battery range has not b... POINT (-121.98609 47.74068) PUGET SOUND ENERGY INC||CITY OF TACOMA - (WA)
112629 1N4BZ1CP7K San Juan Friday Harbor WA NISSAN LEAF Battery Electric Vehicle (BEV) Clean Alternative Fuel Vehicle Eligible POINT (-123.01648 48.53448) BONNEVILLE POWER ADMINISTRATION||ORCAS POWER &...
112630 1FMCU0KZ4N King Vashon WA FORD ESCAPE Plug-in Hybrid Electric Vehicle (PHEV) Clean Alternative Fuel Vehicle Eligible POINT (-122.4573 47.44929) PUGET SOUND ENERGY INC||CITY OF TACOMA - (WA)
112631 KNDCD3LD4J King Covington WA KIA NIRO Plug-in Hybrid Electric Vehicle (PHEV) Not eligible due to low battery range POINT (-122.09124 47.33778) PUGET SOUND ENERGY INC||CITY OF TACOMA - (WA)
112632 YV4BR0CL8N King Covington WA VOLVO XC90 Plug-in Hybrid Electric Vehicle (PHEV) Not eligible due to low battery range POINT (-122.09124 47.33778) PUGET SOUND ENERGY INC||CITY OF TACOMA - (WA)

112633 rows × 10 columns

In [49]:
crosstab_1=pd.crosstab(df['Make'],df['Model'])
px.bar(crosstab_1,orientation='h',height=700)

Observation:¶

  • BMW making more model electric vehicle's like x5,x3,1x,I8,I4,I3,740E,530E,330E.

statistical test¶

Is there a relationship between Make and Country (i.e. Does the preference ofCountry depend on the Making company?)¶

h0:Make and Country has relationship¶

h1:Make and Country has no relationship¶

In [50]:
from scipy.stats import chi2_contingency
from scipy.stats import chi2
In [51]:
observed = pd.crosstab(df.Make,df.County)
In [52]:
chi2_contingency(observed)
Out[52]:
Chi2ContingencyResult(statistic=17206.387705438785, pvalue=0.0, dof=5412, expected_freq=array([[7.24654409e-01, 4.14088233e-02, 1.65635293e-01, ...,
        4.14088233e-02, 2.07044117e-02, 1.27746220e+01],
       [2.17520620e-03, 1.24297497e-04, 4.97189989e-04, ...,
        1.24297497e-04, 6.21487486e-05, 3.83457779e-02],
       [9.32231229e-04, 5.32703559e-05, 2.13081424e-04, ...,
        5.32703559e-05, 2.66351780e-05, 1.64339048e-02],
       ...,
       [1.36882619e+00, 7.82186393e-02, 3.12874557e-01, ...,
        7.82186393e-02, 3.91093196e-02, 2.41304502e+01],
       [7.81209770e-01, 4.46405583e-02, 1.78562233e-01, ...,
        4.46405583e-02, 2.23202791e-02, 1.37716122e+01],
       [7.10981684e-01, 4.06275248e-02, 1.62510099e-01, ...,
        4.06275248e-02, 2.03137624e-02, 1.25335914e+01]]))
In [53]:
chi2_test_stat = chi2_contingency(observed)[0]
pval = chi2_contingency(observed)[1]
df = chi2_contingency(observed)[2]
In [54]:
confidence_level = 0.90

alpha = 1 - confidence_level

chi2_critical = chi2.ppf(1 - alpha, df)

chi2_critical
Out[54]:
5545.751557653358
In [55]:
# Ploting the chi2 distribution to visualise

# Defining the x minimum and x maximum
#plt.figure(figsize=(15,6))
x_min = 5000
x_max = 7000

# Ploting the graph and setting the x limits
x = np.linspace(x_min, x_max, 100)
y = chi2.pdf(x, df)
plt.xlim(x_min, x_max)
plt.plot(x, y)


# Setting Chi2 Critical value
chi2_critical_right = chi2_critical

# Shading the right rejection region
x1 = np.linspace(chi2_critical_right, x_max, 100)
y1 = chi2.pdf(x1, df)
plt.fill_between(x1, y1, color='red')
Out[55]:
<matplotlib.collections.PolyCollection at 0x1cc0107a650>
In [56]:
if(chi2_test_stat > chi2_critical):
    print("Reject Null Hypothesis")
else:
    print("Fail to Reject Null Hypothesis")

Reject Null Hypothesis
In [57]:
if(pval < alpha):
    print("Reject Null Hypothesis")
else:
    print("Fail to Reject Null Hypothesis")

Reject Null Hypothesis
In [60]:
crosstab_2=pd.crosstab(df['Make'],df['County'])
px.bar(crosstab_2,orientation='h',height=700)

Observation:¶

  • In king country having every type of company electrical vehicle so we can say that the electric vehicle buisness most popular in KING country

Conclusion:¶¶

  • Since the p-value is less than the significance level of 0.05, we can reject the null hypothesis. Therefore, we can conclude that there is a no relationship between Make and country.

Task2 (Description) - Create a Choropleth to display the number of EV vehicles based on location.¶

In [61]:
import plotly.graph_objects as go
def create_ev_choropleth_map(df):
    # Calculate the count of EV vehicles for each state
    ev_count_by_state = df['State'].value_counts().reset_index()
    ev_count_by_state.columns = ['State', 'EV Count']

    # Create the Choropleth map using plotly.graph_objects
    fig_choropleth = go.Figure(data=go.Choropleth(
        locations=ev_count_by_state['State'],
        z=ev_count_by_state['EV Count'],
        locationmode='USA-states',
        colorscale='Viridis',
        colorbar_title='Number of EV Vehicles',
    ))

    # Set the map title and layout
    fig_choropleth.update_layout(
        title_text='Choropleth Map of EV Vehicles by State',
        geo_scope='world',
    )


    return fig_choropleth

fig = create_ev_choropleth_map(df)
fig.show()

Task3 (Description) - Create a Racing Bar Plot to display the animation of EV Make and its count each year.¶

In [73]:
pip install bar_chart_race

Collecting bar_chart_race
  Downloading bar_chart_race-0.1.0-py3-none-any.whl (156 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 156.8/156.8 kB 4.2 MB/s eta 0:00:00
Requirement already satisfied: pandas>=0.24 in /usr/local/lib/python3.10/dist-packages (from bar_chart_race) (1.5.3)
Requirement already satisfied: matplotlib>=3.1 in /usr/local/lib/python3.10/dist-packages (from bar_chart_race) (3.7.1)
Requirement already satisfied: contourpy>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib>=3.1->bar_chart_race) (1.1.0)
Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.10/dist-packages (from matplotlib>=3.1->bar_chart_race) (0.11.0)
Requirement already satisfied: fonttools>=4.22.0 in /usr/local/lib/python3.10/dist-packages (from matplotlib>=3.1->bar_chart_race) (4.41.0)
Requirement already satisfied: kiwisolver>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib>=3.1->bar_chart_race) (1.4.4)
Requirement already satisfied: numpy>=1.20 in /usr/local/lib/python3.10/dist-packages (from matplotlib>=3.1->bar_chart_race) (1.22.4)
Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from matplotlib>=3.1->bar_chart_race) (23.1)
Requirement already satisfied: pillow>=6.2.0 in /usr/local/lib/python3.10/dist-packages (from matplotlib>=3.1->bar_chart_race) (8.4.0)
Requirement already satisfied: pyparsing>=2.3.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib>=3.1->bar_chart_race) (3.1.0)
Requirement already satisfied: python-dateutil>=2.7 in /usr/local/lib/python3.10/dist-packages (from matplotlib>=3.1->bar_chart_race) (2.8.2)
Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas>=0.24->bar_chart_race) (2022.7.1)
Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/dist-packages (from python-dateutil>=2.7->matplotlib>=3.1->bar_chart_race) (1.16.0)
Installing collected packages: bar_chart_race
Successfully installed bar_chart_race-0.1.0
In [74]:
import bar_chart_race as bcr
In [75]:
# Converting the 'Model Year' column to datetime type
df['Model Year'] = pd.to_datetime(df['Model Year'], format='%Y')

# Group by 'Model Year' and 'Make' to get the count of each make for each year
df_grouped = df.groupby(['Model Year', 'Make']).size().reset_index(name='Count')



import bar_chart_race as bcr

df_pivot = df_grouped.pivot(index='Model Year', columns='Make', values='Count')

# Fill missing values using forward fill (pad)
df_pivot = df_pivot.fillna(method='pad')

# Create the Racing Bar Plot
bcr.bar_chart_race(
    df=df_pivot,
    filename='ev_make_racing_bar_plot.mp4',
    orientation='h',
    sort='desc',
    n_bars=10,
    fixed_order=False,
    title='EV Make Racing Bar Plot by Year',
    label_bars=True,
    period_label={'x': 0.99, 'y': 0.25, 'ha': 'right', 'va': 'center'},
)

Conclusion¶

  • Every year the frequency will be increased

  • BMW making more model electric vehicle's like x5,x3,1x,I8,I4,I3,740E,530E,330E.

  • Tesla having the maximum electric range that is 337.

  • In the Model Year 2020 having the high electric range that is 337 compare to the other model years.

  • Most of the companies are using Battery ELectric Vehicles comparing witj plug-in-Hybrid electric vehicle.

  • Seattle is the top city in top 10 with electric Cars.

  • King County is the top in top 10 county with more electric Vehicles

  • 98052 postal code contains the high electric cars.

  • JAGUR have the more electric range comapre to other makes.

  • Tesla is the most popular electric car make in Washington state, followed by Nissan, Chevrolet, and Toyota.

  • Tesla is also the most popular make in Seattle, followed by Nissan, Chevrolet, and BMW.

  • Washington state has the highest number of Audi, BMW, and Chevrolet electric cars registered among all states.

In [ ]: